Appndo
All models

Qwen3 235B A22B

QwenOpen weights262K contextTool calling

LMArena score 1366 · #188 overall · #187 in coding (2026-10-13)

Lowest price, from DeepInfra

Per million tokens

Input
$0.18
Output
$0.54
Cached input
—
Batch input / output
—
  • Up to 41K output tokens per request.

Estimate your monthly cost

Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30.

From DeepInfra: $2.88 a month.

Where to buy it (4)

Sorted by your monthly estimate. Prices per million tokens.

  • DeepInfraCheapest

    Input / output
    $0.18 / $0.54
    Context
    41K
    Per month
    $2.88

    deepinfra/Qwen/Qwen3-235B-A22B

  • Nebius

    Input / output
    $0.20 / $0.60
    Context
    262K
    Per month
    $3.20

    nebius/Qwen/Qwen3-235B-A22B

  • Fireworks AI

    Input / output
    $0.22 / $0.88
    Context
    131K
    Per month
    $3.96

    fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b

  • Hyperbolic

    Input / output
    $2.00 / $2.00
    Context
    131K
    Per month
    $24.00

    hyperbolic/Qwen/Qwen3-235B-A22B

Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: Tool calling.

Similar models